Ausif Mahmood

Ausif Mahmood
University of Bridgeport · Department of Computer Science & Engineering

PhD

About

114
Publications
63,849
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,296
Citations
Citations since 2016
54 Research Items
2154 Citations
20162017201820192020202120220100200300400500600
20162017201820192020202120220100200300400500600
20162017201820192020202120220100200300400500600
20162017201820192020202120220100200300400500600
Introduction
Artificial Intelligence, Variational AutoEncoders, Face Recognition, NLP, Reinforcement Learning

Publications

Publications (114)
Article
Full-text available
This article provides a new tool for examining the efficiency and robustness of derivative-free optimization algorithms based on high-dimensional normalized data profiles that test a variety of performance metrics. Unlike the traditional data profiles that examine a single dimension, the proposed data profiles require several dimensions in order to...
Article
Full-text available
Despite the importance of few-shot learning, the lack of labeled training data in the real world makes it extremely challenging for existing machine learning methods because this limited dataset does not well represent the data variance. In this research, we suggest employing a generative approach using variational autoencoders (VAEs), which can be...
Preprint
Full-text available
Despite the importance of few-shot learning, the lack of labeled training data in the real world, makes it extremely challenging for existing machine learning methods as this limited data set does not represent the data variance well. In this research, we suggest employing a generative approach using variational autoencoders (VAEs), which can be us...
Preprint
Full-text available
In recent years, Natural Language Processing (NLP) models have achieved phenomenal success in linguistical and semantical tasks like machine translation, cognitive dialogue systems, information retrieval via Natural Language Understanding (NLU), and Natural Language Generation (NLG). This feat is primarily attributed due to the seminal Transformer...
Article
Full-text available
In recent years, Natural Language Processing (NLP) models have achieved phenomenal success in linguistic and semantic tasks like text classification, machine translation, cognitive dialogue systems, information retrieval via Natural Language Understanding (NLU), and Natural Language Generation (NLG). This feat is primarily attributed due to the sem...
Article
Full-text available
Variational autoencoders (VAEs) are deep latent space generative models that have been im-mensely successful in multiple exciting applications in biomedical informatics such as molecular design, protein design, medical image classification and segmentation, integrated multi-omics data analyses, and large-scale biological sequence analyses, among ot...
Article
Full-text available
Face liveness detection is a critical preprocessing step in face recognition for avoiding face spoofing attacks, where an impostor can impersonate a valid user for authentication. While considerable research has been recently done in improving the accuracy of face liveness detection, the best current approaches use a two-step process of first apply...
Article
Full-text available
Variational Auto-Encoders (VAEs) are deep latent space generative models which have been immensely successful in many applications such as image generation, image captioning, protein design, mu-tation prediction, and language models among others. The fundamental idea in VAEs is to learn the distribu-tion of data in such a way that new meaningful da...
Article
Full-text available
Despite the successful contributions in the field of network intrusion detection using machine learning algorithms and deep networks to learn the boundaries between normal traffic and network attacks, it is still challenging to detect various attacks with high performance. In this paper, we propose a novel mathematical model for further development...
Conference Paper
Only weights and biases are learned by gradient descent-based training of Deep Neural Networks (DNN). The other parameters, i.e., hyperparameters have a huge influence on the quality of the model but finding optimal values for them is not a trivial solution. The hyperparameter space grows exponentially and they also display non-linearity and intera...
Article
Full-text available
Deep learning (DL) is playing an increasingly important role in our lives. It has already made a huge impact in areas such as cancer diagnosis, precision medicine, self-driving cars, predictive forecasting, speech recognition, etc. The painstakingly handcrafted feature extractors used in the traditional learning, classification and pattern recognit...
Article
Full-text available
Face recognition is a popular and efficient form of biometric authentication used in many software applications. One drawback of this technique is that it is prone to face spoofing attacks, where an impostor can gain access to the system by presenting a photograph of a valid user to the sensor. Thus, face liveness detection is a necessary step befo...
Chapter
Cloud Computing (CC) became one of the prominent solutions that organizations do consider to minimize and lean their information technology infrastructure cost by fully utilizing their resources. However, with all the benefits that CC promises, there are many security issues that discourage clients from making the necessary decision to easily embra...
Preprint
Full-text available
Using heterogeneous depth cameras and 3D scanners in 3D face verification causes variations in the resolution of the 3D point clouds. To solve this issue, previous studies use 3D registration techniques. Out of these proposed techniques, detecting points of correspondence is proven to be an efficient method given that the data belongs to the same i...
Article
Full-text available
Differential evolution (DE) has been extensively used in optimization studies since its development in 1995 because of its reputation as an effective global optimizer. DE is a population-based metaheuristic technique that develops numerical vectors to solve optimization problems. DE strategies have a significant impact on DE performance and play a...
Article
Full-text available
Source anonymity in wireless sensor networks (WSNs) becomes a real concern in several applications such as tracking and monitoring. A global adversary that has sophisticated resources, high computation and full view of the network is an obvious threat to such applications. The network and applications need to be protected and secured to provide the...
Article
Full-text available
Face recognition algorithms customarily utilize query faces captured from uncontrolled, in the wild, environments. The quality of these facial images is affected by various internal factors, including the quality of sensors used in outdoor cameras as well as external ones, such as the quality and direction of light. These factors adversely affect t...
Article
Full-text available
We propose a free selective simplex for the downhill Nelder Mead simplex algorithm (1965), rather than the determinant simplex that forces its elements to perform a single operation, such as reflection. Unlike the Nelder-Mead algorithm, the elements of the proposed simplex select various operations of the algorithm to form the next simplex. In this...
Article
Full-text available
Face recognition has become a fascinating field for researchers. The motivation behind the enormous interest in the topic is the need to improve the accuracy of many real-time applications. The complexity of the human face and the changes due to different effects make it more challenging to design as well as implement a powerful computational syste...
Conference Paper
Full-text available
The traveling salesman problem (TSP) can be defined as the process of finding the shortest path for a given set of cities, starting from base city, visiting all other cities once, and returning to the base city. However, when we consider some of the real word problems such as Routing of School bus, the methods that solve the TSP are not effective t...
Article
Full-text available
As the amount of unstructured text data that humanity produces overall and on the internet grows, so does the need to intelligently to process it and extract different types of knowledge from it. Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been applied to Natural Language Processing (NLP) systems with comparative,...
Conference Paper
Full-text available
Natural Language Processing (NLP) systems conventionally treat words as distinct atomic symbols. The model can leverage small amounts of information regarding the relationship between the individual symbols. Today when it comes to texts; one common technique to extract fixed-length features is bag-of-words. Despite its popularity the bag-of-words f...
Article
Full-text available
Explosion phenomena today are considered a significant concern that needs to be detected and analyzed with a prompt response. We develop a multiclass categorization system for explosion phenomena using color images. Consequently, we describe four patterns of explosion phenomena including: pyroclastic density currents, lava fountains, lava and tephr...
Conference Paper
The security of Wireless Sensor Networks (WSNs) is vital in several applications such as the tracking and monitoring of endangered species such as pandas in a national park or soldiers in a battlefield. This kind of applications requires the anonymity of the source, known as Source Location Privacy (SLP). The main aim is to prevent an adversary fro...
Article
Gait recognition is a biometric technique used in determining the identity of humans based on the style and the manner of their walk. Its performance is often degraded by covariate factors such as carrying condition changes, clothing condition changes, and viewing angle variations. Recently, machine learning based techniques have produced promising...
Article
Full-text available
Human gait recognition is a behavioral biometrics method that aims to determine the identity of individuals through the manner and style of their distinctive walk. It is still a very challenging problem because natural human gait is affected by many covariate factors such as changes in the clothing, variations in viewing angle, and changes in carry...
Article
Full-text available
Recent advances in Convolutional Neural Networks (CNNs) have obtained promising results in difficult deep learning tasks. However, the success of a CNN depends on finding an architecture to fit a given problem. A hand-crafted architecture is a challenging, time-consuming process that requires expert knowledge and effort, due to a large number of ar...
Article
Full-text available
A face-spoofing attack occurs when an imposter manipulates a face recognition and verification system to gain access as a legitimate user by presenting a 2D printed image or recorded video to the face sensor. This paper presents an efficient and non-intrusive method to counter face-spoofing attacks that uses a single image to detect spoofing attack...
Conference Paper
Full-text available
Most of the machine learning algorithms requires the input to be denoted as a fixed-length feature vector. In text classifications (bag-of-words) is a popular fixedlength features. Despite their simplicity, they are limited in many tasks; they ignore semantics of words and loss ordering of words. In this paper, we propose a simple and efficient neu...
Article
Full-text available
The need for a proper design and implementation of adequate surveillance system for detecting and categorizing explosion phenomena is nowadays rising as a part of the development planning for risk reduction processes including mitigation and preparedness. In this context, we introduce state-of-the-art explosions classification using pattern recogni...
Conference Paper
Full-text available
Unstructured text data producedon the internet grows rapidly, and sentimentanalysisfor short textsbecomesa challenge because ofthe limit of the contextual information they usually contain. Learning good vector representations for sentencesisachallenging task and an ongoing research area. Moreover, learning long-term dependencies with gradient desce...
Poster
Full-text available
Many of Wireless Sensor Networks (WSNs) applications such as tracking and monitoring endangered species, and/or military applications in areas of interest require anonymity of the origin known as Source Location Privacy (SLP). The aim is to prevent unauthorized observers from tracing the source of a real event by analyzing the traffic on the networ...
Article
Full-text available
Majority of the face recognition algorithms use query faces captured from uncontrolled, in the wild, environment. Often caused by the cameras limited capabilities, it is common for these captured facial images to be blurred or low resolution. Super resolution algorithms are therefore crucial in improving the resolution of such images especially whe...
Conference Paper
Full-text available
This paper describes a simple and efficient Neural Language Model approach for text classification that relies only on unsupervised word representation inputs. Our model employs Recurrent Neural Network Long Short-Term Memory (RNN-LSTM), on top of pre-trained word vectors for sentence-level classification tasks. In our hypothesis we argue that usin...
Conference Paper
This paper presents a novel software architecture for a specialized network simulator that is targeted towards analysis and verification of anonymity algorithms for Wireless Sensor Networks (WSNs). Even though many different network simulators exist and are popular such as NS-2, none of these can be adapted easily for testing of advanced WSN anonym...
Poster
Full-text available
Source Anonymity in WSNs against Global Adversary
Chapter
Cloud Computing (CC) became one of the prominent solutions that organizations do consider to minimizeand lean their information technology infrastructure cost by fully utilizing their resources. However, withall the benefits that CC promises, there are many security issues that discourage clients from makingthe necessary decision to easily embrace...
Article
Full-text available
Wireless sensor networks (WSN) are deployed for many applications such as tracking and monitoring of endangered species, military applications, etc. which require anonymity of the origin, known as Source Location Privacy (SLP). The aim in SLP is to prevent unauthorized observers from tracing the source of a real event by analyzing the traffic in th...
Patent
Full-text available
A system and method of face recognition comprising multiple phases implemented in a parallel architecture. The first phase is a normalization phase whereby a captured image is normalized to the same size, orientation, and illumination of stored images in a preexisting database. The second phase is a feature extraction/distance matrix phase where a...
Conference Paper
Recently, automatic face recognition has been applied in many web and mobile applications. Developers integrate and implement face recognition as an access control into these applications. However, face recognition authentication is vulnerable to several attacks especially when an attacker presents a 2-D printed image or recorded video frames in fr...
Conference Paper
Deep Convolutional Neural networks (ConvNets) have achieved impressive results in several applications of computer vision and speech processing. With the availability of a large training set, it is common to find that the set contains useless samples (instances), either redundant or noisy. The process of removing these instances is called instance...
Conference Paper
Full-text available
Human face recognition and detection has become a very interesting field for the researcher and this interest is motivated by the huge demand of extensive applications of the real time surveillance system and the static matching system like DMV licenses, port authority and bank system. The image processing, neural network and computer vision are th...
Conference Paper
Many of Wireless Sensor Networks (WSNs) applications such as tracking and monitoring endangered species, and/or military applications in areas of interest require anonymity of the origin known as Source Location Privacy (SLP). The aim is to prevent unauthorized observers from tracing the source of a real event by analyzing the traffic on the networ...
Article
Full-text available
Genetic Algorithm (GA) is a metaheuristic used in solving combinatorial optimization problems. Inspired by evolutionary biology, GA uses selection, crossover, and mutation operators to efficiently traverse the solution search space. This paper proposes nature inspired fine-tuning to the crossover operator using the untapped idea of Mitochondrial DN...
Chapter
Full-text available
Computing the optimal geometric structure of manipulators is one of the most intricate problems in contemporary robot kinematics. Robotic manipulators are designed and built to perform certain predetermined tasks. There is a very close relationship between the structure of the manipulator and its kinematic performance. It is therefore important to...
Article
Full-text available
Wireless sensor network (WSN) consists of many hosts called sensors. These sensors can sense a phenomenon (motion, temperature, humidity, average, max, min, etc.) and represent what they sense in a form of data. There are many applications for WSNs including object tracking and monitoring where in most of the cases these objects need protection. In...
Conference Paper
Full-text available
One of the limitations of the existing face recognition algorithms is that the recognition rate significantly decreases with the increase in dataset size. In order to eliminate this shortcoming, this paper presents a new training dataset partitioning methodology to improve face recognition for large datasets. This methodology is then applied to the...
Article
Gait recognition is a biometric method used to recognize humans based on the style of their walk. In the last few years, wide varieties of gait recognition approaches have been proposed, and significant improvements have been made. Unlike other biometric methods, such as face and body recognition, gait recognition requires dealing with a large numb...
Article
Object detection is an important area of research in computer vision. One of the most popular approaches for object detection is based on combining many weak classifiers together to achieve one strong classifier through a technique called Boosting. A modified version of this technique for real-time face detection was developed by Viola and Jones, w...
Article
Controlling secure access to web Application Programming Interfaces (APIs) and web services has become more vital with advancement and use of the web technologies. The security of web services APIs is encountering critical issues in managing authenticated and authorized identities of users. Open Authorization (OAuth) is a secure protocol that allow...
Article
Full-text available
Magnetotactic bacteria (MTB), discovered in early 1970s contain single-domain crystals of magnetite (Fe3O4) called magnetosomes that tend to form a chain like structure from the proximal to the distal pole along the long axis of the cell. The ability of these bacteria to sense the magnetic field for displacement, also called magnetotaxis, arises fr...
Article
Steganalysis deals with detecting the presence of hidden information in different types of media such as images and audio files. Such detection is very challenging because of the variety of algorithms that might be used in embedding secret information in a media type. This chapter presents a reliable Steganalyzer system with distributed services or...
Article
Full-text available
AdaBoost is an important algorithm in machine learning and is being widely used in object detection. AdaBoost works by iteratively selecting the best amongst weak classifiers, and then combines several weak classifiers to obtain a strong classifier. Even though AdaBoost has proven to be very effective, its learning execution time can be quite large...
Chapter
Steganography is the art of hiding a secret object in a cover media, while Steganalysis is the art of discovering the secret object from the cover media. With the increased emphasis in security, both steganography and steganalysis have recently drawn great research attention. While it is relatively easy to embed a secret message in a media such as...
Article
Full-text available
This paper presents a unified Steganalyzer that can work with different media types such as images and audios. It is also capable of providing improved accuracy in stego detection through the use of multiple algorithms. The designed system integrates different steganalysis techniques in a reliable Steganalyzer by using a Services Oriented Architect...
Book
Full-text available
Technological Developments in Networking, Education and Automation includes a set of rigorously reviewed world-class manuscripts addressing and detailing state-of-the-art research projects in the following areas: Computer Networks: Access Technologies, Medium Access Control, Network architectures and Equipment, Optical Networks and Switching, Tele...
Book
Full-text available
Novel Algorithms and Techniques in Telecommunications and Networking includes a set of rigorously reviewed world-class manuscripts addressing and detailing state-of-the-art research projects in the areas of Industrial Electronics, Technology & Automation, Telecommunications and Networking. Novel Algorithms and Techniques in Telecommunications and...
Book
Full-text available
Novel Algorithms and Techniques in Telecommunications, Automation and Industrial Electronics includes a set of rigorously reviewed world-class manuscripts addressing and detailing state-of-the-art research projects in the areas of Industrial Electronics, Technology & Automation, Telecommunications and Networking. Novel Algorithms and Techniques in...
Book
Full-text available
Innovative Algorithms and Techniques in Automation, Industrial Electronics and Telecommunications is a collection of world class paper articles addressing the following topics: Computer Networks: Access Technologies, Medium Access Control, Network architectures and Equipment, Optical Networks and Switching, Telecommunication Technology, and Ultra...
Book
Innovative Algorithms and Techniques in Automation, Industrial Electronics and Telecommunications is a collection of world class paper articles addressing the following topics: • Computer Networks: Access Technologies, Medium Access Control, Network architectures and Equipment, Optical Networks and Switching, Telecommunication Technology, and Ultr...
Book
Full-text available
include a set of rigorously reviewed world-class manuscripts addressing and detailing state-of-the-art research projects in the areas of: Industrial Electronics, Technology and Automation, Telecommunications, Networking, Engineering Education, Instructional Technology and e-Learning. The three conferences, (IETA 05, TENE 05 and EIAE 05) were part...
Book
Full-text available
The conference proceedings of: • International Conference on Industrial Electronics, Technology & Automation (IETA 05) • International Conference on Telecommunications and Networking (TeNe 05) • International Conference on Engineering Education, Instructional Technology, Assessment, and E-learning (EIAE 05) include a set of rigorously reviewed...
Conference Paper
This paper develops a new parallel algorithm for computing the inverse of a banded matrix when extended in its maximum entropy sense. The algorithm developed here computes the inverse in two parallel steps. The first parallel step uses a modified Schur's complement technique to compute the individual inverses in each of the block matrices in parall...
Article
This work examines closely the possibilities for errors, mistakes and uncertainties in sensing systems. We identify and suggest techniques for modeling, analyzing, and recovering these uncertainties. This work concentrates on uncertainties in visual sensing for manipulators. The goal is to recover 3-D structure and motion characteristics of the env...
Article
Time delays are an integral part of high-speed circuits and control-system applications. Rational approximations to the Laplace transform of a time delay T<sub>d</sub>, i.e., e-T(d<sup>s</sup>) have been used in the past. These approximations include Pade, Bessel, and other variations. The disadvantage of such approximations is that the quality of...